International Journal of Pattern Recognition and Artificial Intelligence

The analysis and recognition of 2D shapes using the orthogonal complex AR model has been extended for the recognition of arbitrary 3D objects. A 3D object is placed at one of its stable orientation and sectioned into a fixed number of "slices" of equal thickness in such a way that the "slices" are parallel to the object's stable plane. The surface of an object can be represented by a sequence of these parallel 2D closed contours. A complex AR model is then fitted to each of these contours. An orthogonal estimator is implemented to determine the correct model order and to estimate the associated model parameters. The estimated AR model parameters, magnitude ratios and the relative centroid associated with each 2D contour are used as essential features for 3D object recognition. An algorithm with hierarchical structure for the recognition of 3D objects is derived based on matching the sequence of 2D contours. Simulation studies are included to show the effectiveness of different criteria being applied at different stages of the recognition process. Test results have shown that the proposed approach can provide a feasible and effective means for recognizing arbitrary 3D objects which can be self-occluded and have a number of stable orientation.

There is wide application for the extraction of textual information from low-contrast, complex natural images. We are particularly interested in segmentation and thresholding algorithms for use in a portable text-to-speech system for the vision impaired. Reading low-contrast LCD displays is the target application. We present a low-complexity method for automatically extracting text of any size, font, and format from images acquired by a video camera that may be poorly focused and aimed, under conditions of inadequate and uneven illumination. The new method consists of fast thresholding that combines a local variance measure with a logical stroke-width method, and with a low-complexity statistical and contextual noise segmentation. The performance of this method compares favorably with more complex methods for the extraction of characters from scene images. Initial results are encouraging for application in a robust portable reader.

A new head tracking algorithm for automatically detecting and tracking human heads in complex backgrounds is proposed. By using an elliptical model for the human head, our Maximum Likelihood (ML) head detector can reliably locate human heads in images having complex backgrounds and is relatively insensitive to illumination and rotation of the human heads. Our head detector consists of two channels: the horizontal and the vertical channels. Each channel is implemented by multiscale template matching. Using a hierarchical structure in implementing our head detector, the execution time for detecting the human heads in a 512×512 image is about 0.02 second in a Sparc 20 workstation (not including the time for image acquisition). Based on the ellipse-based ML head detector, we have developed a head tracking method that can monitor the entrance of a person, detect and track the person's head, and then control the stereo cameras to focus their gaze on this person's head. In this method, the ML head detector and the mutually-supported constraint are used to extract the corresponding ellipses in a stereo image pair. To implement a practical and reliable face detection and tracking system, further verification using facial features, such as eyes, mouth and nostrils, may be essential. The 3D position computed from the centers of the two corresponding ellipses is then used for fixation. An active stereo head has been used to perform the experiments and has demonstrated that the proposed approach is feasible and promising for practical uses.

In this paper, a vision-based system for underwater object detection is presented. The system is able to detect automatically a pipeline placed on the sea bottom, and some objects, e.g. trestles and anodes, placed in its neighborhoods. A color compensation procedure has been introduced in order to reduce problems connected with the light attenuation in the water. Artificial neural networks are then applied in order to classify in real-time the pixels of the input image into different classes, corresponding e.g. to different objects present in the observed scene. Geometric reasoning is applied to reduce the detection of false objects and to improve the accuracy of true detected objects. The results on real underwater images representing a pipeline structure in different scenarios are shown. The presence of seaweed and sand, different illumination conditions and water depth, different pipeline diameter and small variations of the camera tilt angle are considered to evaluate the algorithm performances.

In this paper we propose a method for increasing precision and reliability of elasticity analysis in complicated burn scar cases. The need for a technique that would help physicians by objectively assessing elastic properties of scars, motivated our original algorithm. This algorithm successfully employed active contours for tracking and finite element models for strain analysis. However, the previous approach considered only one normal area and one abnormal area within the region of interest, and scar shapes which were somewhat simplified. Most burn scars have rather complicated shapes and may include multiple regions with different elastic properties. Hence, we need a method capable of adequately addressing these characteristics. The new method can split the region into more than two localities with different material properties, select and quantify abnormal areas, and apply different forces if it is necessary for a better shape description of the scar. The method also demonstrates the application of scale and mesh refinement techniques in this important domain. It is accomplished by increasing the number of Finite Element Method (FEM) areas as well as the number of elements within the area.

The method is successfully applied to elastic materials and real burn scar cases. We demonstrate all of the proposed techniques and investigate the behavior of elasticity function in a 3-D space. Recovered properties of elastic materials are compared with those obtained by a conventional mechanics-based approach. Scar ratings achieved with the method are correlated against the judgments of physicians.

A hybrid neural network architecture is investigated for classification purposes. The proposed hybrid is based on the multilayer perceptron (MLP) network. In addition to the usual hidden layers the first hidden layer is selected to be an adaptive centroid layer. Each unit in this new layer incorporates a centroid vector that is located somewhere in the space spanned by the input variables. The output of these units is the Euclidean distance between the centroid vector and the inputs. The centroid layer has some resemblance to the hidden layer of the radial basis function (RBF) networks. Therefore the proposed design can be regarded as a sort of hybrid of the MLP and RBF networks. The presented benchmark experiments demonstrate that the proposed hybrid can provide significant advantages over standard MLPs in terms of fast and efficient learning, and compact network structure.

In this research a computer vision-based shape recognition system which combines an image projection and the back propagation neural network is proposed. The system uses the image projection and features of the projection histogram to represent the shape, and uses the back propagation neural network to classify the shape. In this research, a fast normalization scheme is developed which is especially designed for image projection and can also find the same projection axis no matter what the object's orientation. Therefore, the proposed system can be invariant to scale, translation, and orientation variations. This research finds that the direct representation scheme of the back propagation neural net has better accuracy than the binary coding representation scheme. This research also finds that the proposed system's classification accuracy is greater than 98.8% and its processing speed is also very fast. Therefore, the proposed system is feasible for use in shape classification, in practice.

Most of the previous polygonal approximation methods are sub-optimal and their compression ratio with respect to a given error tolerance is not good enough for some applications. Recently, a genetic-based approach which can provide near-optimal solutions is presented, but the demands on computation and memory are too high. In this paper, a new polygonal approximation method using the tabu search technique is presented. The proposed method produces a higher compression ratio than the suboptimal approach and the genetic-based approach, and the computation cost and the memory store are more efficient.